Use of non-linear prediction tools to assess rock mass permeability using various discontinuity parameters

Abstract Because of complex discontinuity patterns, it is almost impossible to determine the permeability of rock masses if no proper testing methodology is used. As available in the literature, many empirical approaches to estimate the permeability of a rock mass have been proposed. There is no publication, however, that uses regression analyses and ANFIS (Adaptive Neuro-Fuzzy Inference System) modeling to determine the rock mass permeability. The purpose of the study is to develop various ANFIS and multiple regression models to estimate the rock mass permeability. To this end, a dataset including 453 cases with Lugeon test results and corresponding RQD (Rock Quality Designation), spacing of discontinuities and SCR (Surface Condition Rating) properties is employed. The data were obtained from granite, diorite, volcanic breccia, andesite and agglomerate rock masses from various dam sites and a coal mine in Turkey. Whole data were randomly divided into two parts for training and testing. Two different models were developed to estimate the rock mass permeability. The inputs of the first model are RQD and SCR (Model 1), and the inputs of the second model are discontinuity spacing and SCR (Model 2). Simple regression analyses indicate that there is no statistically meaningful relationship between the Lugeon values with discontinuity spacing and SCR. There is a statistically meaningful relationship, however, between the Lugeon values and RQD. Non-linear multiple regression analyses were implemented for two independent variables and a dependent variable because of the non-linear relationships between the inputs and the output. ANFIS was employed as a second non-linear tool to construct prediction models. According to the performance assessments of the developed models, both of the models and all of the sets are successful. ANFIS is a more successful tool than NLMR. These results show that the models developed are reliable enough and, if there is no direct test result, these models can be used in engineering projects.

[1]  Candan Gokceoglu,et al.  Application of fuzzy inference system and nonlinear regression models for predicting rock brittleness , 2010, Expert Syst. Appl..

[2]  D. T. Snow.  ROCK FRACTURE SPACINGS, OPENINGS, AND POROSITIES , 1968 .

[3]  Chaoshui Xu,et al.  A comparative study for empirical equations in estimating deformation modulus of rock masses , 2012 .

[4]  Nick Barton,et al.  Some new Q-value correlations to assist in site characterisation and tunnel design , 2002 .

[5]  Mostafa Sharifzadeh,et al.  Application of soft granulation theory to permeability analysis , 2009 .

[6]  O. Zienkiewicz,et al.  Rock mechanics in engineering practice , 1968 .

[7]  T. N. Singh,et al.  Estimation of elastic constant of rocks using an ANFIS approach , 2012, Appl. Soft Comput..

[8]  Ebru Akcapinar Sezer,et al.  Application of two non-linear prediction tools to the estimation of tunnel boring machine performance , 2009, Eng. Appl. Artif. Intell..

[9]  J. L. Huitt.  Fluid flow in simulated fractures , 1956 .

[10]  W. T. Illingworth,et al.  Practical guide to neural nets , 1991 .

[11]  Ebru Akcapinar Sezer,et al.  Artificial neural networks and nonlinear regression techniques to assess the influence of slake durability cycles on the prediction of uniaxial compressive strength and modulus of elasticity for carbonate rocks , 2012 .

[12]  J. Sharp,et al.  Fluid flow through fissured media , 1970 .

[13]  Kevin Swingler,et al.  Applying neural networks - a practical guide , 1996 .

[14]  C. Gokceoğlu,et al.  Predicting the deformation moduli of rock masses , 2003 .

[15]  R. Reyment,et al.  Statistics and Data Analysis in Geology. , 1988 .

[16]  Cheng-Haw Lee,et al.  A simple method of estimating rock mass porosity and permeability , 1990 .

[17]  M. A. Sánchez,et al.  A proposal for a Secondary Permeability Index obtained from water pressure tests in dam foundations , 2005 .

[18]  K. Diamantis,et al.  Study on uniaxial compressive strength, point load strength index, dynamic and physical properties of serpentinites from Central Greece: Test results and empirical relations , 2009 .

[19]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[20]  D. Wyllie,et al.  Rock Slope Engineering: Fourth Edition , 2004 .

[21]  J. Keaton.  Rock Slope Engineering: Civil and Mining, 4th Edition , 2007 .

[22]  Carl G. Looney,et al.  Advances in Feedforward Neural Networks: Demystifying Knowledge Acquiring Black Boxes , 1996, IEEE Trans. Knowl. Data Eng..

[23]  S. Chehreh Chelgani,et al.  Studies of relationships between Free Swelling Index (FSI) and coal quality by regression and Adaptive Neuro Fuzzy Inference System , 2011 .

[24]  E. T. Brown.  Rock characterization, testing & monitoring: ISRM suggested methods , 1981 .

[25]  Evert Hoek,et al.  Practical estimates of rock mass strength , 1997 .

[26]  Ahmed Ouenes,et al.  Practical application of fuzzy logic and neural networks to fractured reservoir characterization , 2000 .

[27]  Ebru Akcapinar Sezer,et al.  Prediction of uniaxial compressive strength of granitic rocks by various nonlinear tools and comparison of their performances , 2013 .

[28]  Candan Gokceoglu,et al.  Estimating the uniaxial compressive strength of some clay‐bearing rocks selected from Turkey by nonlinear multivariable regression and rule‐based fuzzy models , 2009, Expert Syst. J. Knowl. Eng..

[29]  Jong-Se Lim,et al.  Reservoir Permeability Determination using Artificial Neural Network , 2003 .

[30]  C. Gokceoğlu,et al.  Estimating the deformation modulus of rock masses: a comparative study , 2003 .

[31]  I. Yilmaz,et al.  Prediction of the strength and elasticity modulus of gypsum using multiple regression, ANN, and ANFIS models , 2009 .

[32]  J. Hower,et al.  Estimation of free-swelling index based on coal analysis using multivariable regression and artifici , 2011 .

[33]  Resat Ulusay,et al.  Modifications to the geological strength index (GSI) and their applicability to stability of slopes , 1999 .

[34]  Saro Lee,et al.  Application of an adaptive neuro-fuzzy inference system to ground subsidence hazard mapping , 2012, Comput. Geosci..

[35]  Altay Acar,et al.  Estimation of strength and deformation properties of Quaternary caliche deposits , 2008 .

[36]  Biswajeet Pradhan,et al.  Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping: Klang valley, Malaysia , 2011, Expert Syst. Appl..

[37]  Ebru Akcapinar Sezer,et al.  Modeling of the uniaxial compressive strength of some clay-bearing rocks using neural network , 2011, Appl. Soft Comput..

[38]  Ali Firat Cabalar,et al.  Some applications of Adaptive Neuro-Fuzzy Inference System (ANFIS) in geotechnical engineering , 2012 .

[39]  Ali Akbar Asrari,et al.  The performance of ANFIS model for prediction of deformation modulus of rock mass , 2013, Arabian Journal of Geosciences.

[40]  T. N. Singh,et al.  A neuro-fuzzy approach for prediction of longitudinal wave velocity , 2012, Neural Computing and Applications.

[41]  Ebru Akcapinar Sezer,et al.  An application of adaptive neuro fuzzy inference system for estimating the uniaxial compressive strength of certain granitic rocks from their mineral contents , 2013, Expert Syst. Appl..

[42]  K. Terzaghi,et al.  Soil mechanics in engineering practice , 1948 .